Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    occurrences of mathematical symbols and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ron
    -0.55
    ity
    -0.49
    DS
    -0.48
    ...
    -0.48
     Siro
    -0.47
     segn
    -0.46
     global
    -0.46
     ...
    -0.45
    Ron
    -0.44
     Or
    -0.44
    POSITIVE LOGITS
    abestanden
    1.02
    \{\\
    0.91
     }}$}
    0.88
    Clik
    0.88
     ་་
    0.88
    +#+#
    0.85
     $_{\
    0.85
    ']))
    0.84
    Hochspringen
    0.82
     Мексичка
    0.82
    Act Density 0.671%

    No Known Activations